Building mixed lingual speech synthesis systems
These are a series of projects that we are working on with an aim to build voices capable of rendering codemixed content.
These are a series of projects that we are working on with an aim to build voices capable of rendering codemixed content.
The initial part of this work was accepted for presentation at Interspeech 2017 in Stockholm. I have written a blogpost about this. You can track the updates in the project on ResearchGate.
We have built Android applications that can render the bilingual content in an effective way. These apps are a visualization of jarvis on phone, and are built using Google APIs. Check them out: Telugu Tamil Punjabi Marathi Kannada Gujarati